llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsNemotron 3 Ultra

NVIDIA model product

Nemotron 3 Ultra

Nemotron 3 Ultra is NVIDIA's frontier-scale open model with 550B total / 55B active parameters, built for agentic reasoning, long-context analysis, tool use, and high-stakes RAG. It uses a hybrid Latent Mixture-of-Experts (LatentMoE) architecture interleaving Mamba-2, MoE, and select Attention layers, with Multi-Token Prediction (MTP) for native speculative decoding, and is pre-trained on ~20T tokens with an NVFP4 recipe. Reasoning is configurable on/off (plus a medium-effort mode) via the chat template. It supports up to a 1M-token context and 10 languages (English, French, Spanish, Italian, German, Japanese, Hindi, Korean, Brazilian Portuguese, Chinese). Released with open weights, training data, and recipes under the OpenMDW-1.1 license.

Updated Aug 10, 2026. Default version: Nemotron 3 Ultra (550B A55B)

Compare
LLMBoard score72.1Nemotron 3 Ultra (550B A55B)
Coverage100%10 benchmark families
Context window1MTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Nemotron 3 Ultra (550B A55B)
Released
Jun 4, 2026
Knowledge cutoff
Sep 30, 2025
Parameters
550B
Context window
1M
Max output
128K
Inputs
text
Outputs
text
Open weights
Yes
License
OpenMDW License v1.1

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Nemotron 3 Ultra (550B A55B) category scores

Benchmark results

Published benchmark records for the scored version Nemotron 3 Ultra (550B A55B).

26 rows
Columns

Show columns

Apex0.812100.0%CAug 7, 2026
IMO-AnswerBench0.9119100.0%CAug 7, 2026
OmniScience0.812100.0%CAug 7, 2026
PinchBench0.914100.0%CAug 7, 2026
ProfBench0.611100.0%CAug 7, 2026
RULER0.914100.0%CAug 7, 2026
IFBench0.822896.3%CAug 7, 2026
GDPval0.5330.0%CAug 7, 2026
CritPT0.0440.0%CAug 7, 2026
LiveCodeBench v60.945394.2%CAug 7, 2026
LongBench v20.641781.3%CAug 7, 2026
MMLU-ProX0.853287.1%CAug 7, 2026
TAU3-Bench0.2550.0%CAug 7, 2026
Multi-Challenge0.662982.1%CAug 7, 2026
WMT24++0.862377.3%CAug 7, 2026
AA-LCR0.781550.0%CAug 7, 2026
Finance Agent0.5880.0%CAug 7, 2026
MMLU-Pro0.9912993.8%CAug 7, 2026
SciCode0.491852.9%CAug 7, 2026
Terminal-Bench 2.10.616176.3%CAug 7, 2026
Finance Agent v20.4202624.0%BAug 7, 2026
SWE-bench Multilingual0.7213439.4%CAug 7, 2026
Humanity's Last Exam0.4379260.4%CAug 7, 2026
GPQA0.94223382.3%CAug 7, 2026
BrowseComp0.4495815.8%CAug 7, 2026
SWE-Bench Verified0.75610446.6%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

No published Arena match

The default version has no published Arena rows, or its source alias has not been resolved.

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
1
1 rows
Columns

Show columns

Kenarinemotron-3-ultra-550b-a55bglobalN/AN/A1MAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Nemotron 3 Ultra versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Nemotron 3 Ultra (550B A55B)Jun 4, 202672.1550B1M128KYesOpenMDW License v1.1

What is Nemotron 3 Ultra?

A concise description based on the published model registry.

Nemotron 3 Ultra is NVIDIA's frontier-scale open model with 550B total / 55B active parameters, built for agentic reasoning, long-context analysis, tool use, and high-stakes RAG. It uses a hybrid Latent Mixture-of-Experts (LatentMoE) architecture interleaving Mamba-2, MoE, and select Attention layers, with Multi-Token Prediction (MTP) for native speculative decoding, and is pre-trained on ~20T tokens with an NVFP4 recipe. Reasoning is configurable on/off (plus a medium-effort mode) via the chat template. It supports up to a 1M-token context and 10 languages (English, French, Spanish, Italian, German, Japanese, Hindi, Korean, Brazilian Portuguese, Chinese). Released with open weights, training data, and recipes under the OpenMDW-1.1 license.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Nemotron 3 Ultra vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Nemotron 3 UltravsGemini 3 FlashNemotron 3 UltravsQwen3.6 PlusNemotron 3 UltravsQwen3.6 27BNemotron 3 UltravsDeepSeek-V4-FlashNemotron 3 UltravsKimi K2.5Nemotron 3 UltravsGPT-5

Models similar to Nemotron 3 Ultra

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#46-9.5
NV

Llama 3.3 Nemotron Super 49B

NVIDIA

62.6 LLMBoard

DetailsCompare
#47-9.6
NV

Llama 3.1 Nemotron Ultra 253B

NVIDIA

62.6 LLMBoard

DetailsCompare
#52-10.9
NV

Nemotron Nano 9B

NVIDIA

61.2 LLMBoard

DetailsCompare
#54-13.1
NV

Nemotron 3 Super

NVIDIA

59.1 LLMBoard

DetailsCompare
#97-27.0
NV

Nemotron 3 Nano

NVIDIA

45.1 LLMBoard

DetailsCompare
#100-28.0
NV

Llama 3.1 Nemotron Nano 8B

NVIDIA

44.2 LLMBoard

DetailsCompare

FAQ

Common questions about Nemotron 3 Ultra.

When was Nemotron 3 Ultra released?

Nemotron 3 Ultra's default version was released on Jun 4, 2026.

How much does Nemotron 3 Ultra cost?

No official standard PAYG price is currently available for Nemotron 3 Ultra.

Who created Nemotron 3 Ultra?

Nemotron 3 Ultra is published under NVIDIA in the model registry.

What is the context window for Nemotron 3 Ultra?

The default version has a 1M token context window.

Is Nemotron 3 Ultra open weight?

Yes. The default version is marked as open weight under OpenMDW License v1.1.

How many API providers offer Nemotron 3 Ultra?

1 published provider offerings are linked to the default version.

What models should I compare Nemotron 3 Ultra with?

Nearby ranked alternatives include Gemini 3 Flash, Qwen3.6 Plus, Qwen3.6 27B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai